bkonold commented on a change in pull request #1385:
URL: https://github.com/apache/samza/pull/1385#discussion_r443893701
##########
File path:
samza-core/src/main/scala/org/apache/samza/storage/ContainerStorageManager.java
##########
@@ -758,41 +744,50 @@ public void run() {
sideInputSystemConsumers.register(ssp, startingOffset);
taskInstanceMetrics.get(this.sspSideInputHandlers.get(ssp).getTaskName()).addOffsetGauge(
ssp, ScalaJavaUtil.toScalaFunction(() ->
this.sspSideInputHandlers.get(ssp).getLastProcessedOffset(ssp)));
+
sideInputTaskMetrics.get(this.sspSideInputHandlers.get(ssp).getTaskName()).addOffsetGauge(
+ ssp, ScalaJavaUtil.toScalaFunction(() ->
this.sspSideInputHandlers.get(ssp).getLastProcessedOffset(ssp)));
+ }
- SystemStreamMetadata systemStreamMetadata =
streamMetadataCache.getSystemStreamMetadata(ssp.getSystemStream(), false);
- SystemStreamMetadata.SystemStreamPartitionMetadata sspMetadata =
- (systemStreamMetadata == null) ? null :
systemStreamMetadata.getSystemStreamPartitionMetadata().get(ssp.getPartition());
+ Map<TaskName, TaskSideInputHandler> taskSideInputHandlers =
this.sspSideInputHandlers.values().stream()
+ .distinct()
+ .collect(Collectors.toMap(TaskSideInputHandler::getTaskName,
Function.identity()));
- // record a copy of the sspMetadata, to later check if its caught up
- initialSideInputSSPMetadata.put(ssp, sspMetadata);
+ Map<TaskName, RunLoopTask> sideInputTasks = new HashMap<>();
+ this.taskSideInputStoreSSPs.forEach((taskName, storesToSSPs) -> {
+ Set<SystemStreamPartition> taskSSPs =
this.taskSideInputStoreSSPs.get(taskName).values().stream()
+ .flatMap(Set::stream)
+ .collect(Collectors.toSet());
- // check if the ssp is caught to upcoming, even at start
- checkSideInputCaughtUp(ssp, startingOffset,
SystemStreamMetadata.OffsetType.UPCOMING, false);
- }
+ RunLoopTask sideInputTask = new SideInputTask(taskName, taskSSPs,
taskSideInputHandlers.get(taskName), sideInputTaskMetrics.get(taskName));
+
+ sideInputTasks.put(taskName, sideInputTask);
+ });
// start the systemConsumers for consuming input
this.sideInputSystemConsumers.start();
+ TaskConfig taskConfig = new TaskConfig(this.config);
+ SamzaContainerMetrics sideInputContainerMetrics =
+ new SamzaContainerMetrics(SIDEINPUTS_METRICS_PREFIX +
this.samzaContainerMetrics.source(),
+ this.samzaContainerMetrics.registry());
+
+ this.sideInputRunLoop = new RunLoop(sideInputTasks,
+ null, // all operations are executed in the main runloop thread
+ this.sideInputSystemConsumers,
+ 1, // single message in flight per task
+ -1, // no windowing
+ taskConfig.getCommitMs(),
+ taskConfig.getCallbackTimeoutMs(),
+ 1, // default taken from SamzaContainer
Review comment:
This is a good catch. Perhaps I should just refactor the config access
from `SamzaContainer` into a config class and reuse the method here. Thoughts?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
